{"id":"https://openalex.org/W4320067900","doi":"https://doi.org/10.1145/3545008.3545022","title":"Characterizing and Optimizing Transformer Inference on ARM Many-core Processor","display_name":"Characterizing and Optimizing Transformer Inference on ARM Many-core Processor","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4320067900","doi":"https://doi.org/10.1145/3545008.3545022"},"language":"en","primary_location":{"id":"doi:10.1145/3545008.3545022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048148542","display_name":"Jiazhi Jiang","orcid":"https://orcid.org/0000-0002-1417-3012"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiazhi Jiang","raw_affiliation_strings":["Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024085713","display_name":"Jiangsu Du","orcid":"https://orcid.org/0000-0003-4707-9492"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiangsu Du","raw_affiliation_strings":["Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041534890","display_name":"Dan Huang","orcid":"https://orcid.org/0000-0001-5582-1031"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Huang","raw_affiliation_strings":["Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100440903","display_name":"Dongsheng Li","orcid":"https://orcid.org/0000-0001-9743-2034"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongsheng Li","raw_affiliation_strings":["Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101733890","display_name":"Zheng Jiang","orcid":"https://orcid.org/0009-0009-4718-2933"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang Zheng","raw_affiliation_strings":["Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101633465","display_name":"Yutong Lu","orcid":"https://orcid.org/0000-0001-5315-3375"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Lu","raw_affiliation_strings":["Sun Yat-Sen University, China"],"affiliations":[{"raw_affiliation_string":"Sun Yat-Sen University, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5048148542"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":1.8678,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8547837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7656383514404297},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7371206283569336},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6881389617919922},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6012956500053406},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5597535371780396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5583500266075134},{"id":"https://openalex.org/keywords/arm-architecture","display_name":"ARM architecture","score":0.5527200698852539},{"id":"https://openalex.org/keywords/de-facto","display_name":"De facto","score":0.5149891972541809},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4803101420402527},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.46906542778015137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4425259232521057},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.435238242149353},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3576538562774658},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3541403114795685},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.29340726137161255},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2789372503757477},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13292992115020752},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.13224324584007263},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.07796493172645569}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7656383514404297},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7371206283569336},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6881389617919922},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6012956500053406},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5597535371780396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5583500266075134},{"id":"https://openalex.org/C26771161","wikidata":"https://www.wikidata.org/wiki/Q16980","display_name":"ARM architecture","level":2,"score":0.5527200698852539},{"id":"https://openalex.org/C2992317946","wikidata":"https://www.wikidata.org/wiki/Q712144","display_name":"De facto","level":2,"score":0.5149891972541809},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4803101420402527},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.46906542778015137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4425259232521057},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.435238242149353},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3576538562774658},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3541403114795685},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29340726137161255},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2789372503757477},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13292992115020752},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.13224324584007263},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.07796493172645569},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3545008.3545022","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6100000143051147,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2084379367","https://openalex.org/W2475126267","https://openalex.org/W2888498443","https://openalex.org/W2924040443","https://openalex.org/W2970971581","https://openalex.org/W3114874950","https://openalex.org/W3130716829","https://openalex.org/W3164865299","https://openalex.org/W3195800062","https://openalex.org/W3210601829"],"related_works":["https://openalex.org/W4248999141","https://openalex.org/W4255057712","https://openalex.org/W2126398188","https://openalex.org/W4251458280","https://openalex.org/W1582746211","https://openalex.org/W2512412909","https://openalex.org/W1547865754","https://openalex.org/W2116570023","https://openalex.org/W4210605172","https://openalex.org/W4245707462"],"abstract_inverted_index":{"Transformer":[0,63],"has":[1,16],"experienced":[2],"tremendous":[3],"success":[4],"and":[5],"revolutionized":[6],"the":[7,18],"field":[8],"of":[9],"natural":[10],"language":[11],"processing":[12],"(NLP).":[13],"While":[14],"GPU":[15],"become":[17],"de":[19],"facto":[20],"standard":[21],"for":[22,37,55],"deep":[23,38],"learning":[24,39],"computation":[25],"in":[26],"many":[27,32],"cases,":[28],"there":[29],"are":[30],"still":[31],"scenarios":[33],"where":[34],"using":[35],"CPU":[36],"remains":[40],"a":[41,52],"prevalent":[42],"choice.":[43],"In":[44],"particular,":[45],"ARM":[46],"many-core":[47],"processor":[48],"is":[49,59],"emerging":[50],"as":[51],"competitive":[53],"candidate":[54],"HPC":[56],"systems,":[57],"which":[58],"promising":[60],"to":[61],"deploy":[62],"inference.":[64]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}
